Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Bumblebiber/its-over-9k/plugin install o9k-coreWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/bumblebiber/its-over-9k/o9k-init)<a href="https://agentmods.dev/skills/bumblebiber/its-over-9k/o9k-init"><img src="https://agentmods.dev/badge/skills/bumblebiber/its-over-9k/o9k-init.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00080 | $0.05912 |
| Opus 5 | $0.00040 | $0.02956 |
| Sonnet 5 | $0.00016 | $0.01182 |
| Haiku 4.5 | $0.00008 | $0.00591 |
Grade C, and why
o9k-init scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
Ask, don't lecture. One question at a time, options not essays. In order: Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Linux: `sudo apt-get install -y git` / `dnf install -y git` / How it starts
The opening of the file, as written. The whole thing — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.
o9k-init — Guided Setup
The one flow that takes a machine from "just added the marketplace" to a
conflict-free stack of exactly the pieces this user wants. It detects before it
asks, asks before it acts, and never destroys data. /o9k-guide explains a
setup; /o9k-init builds one. After /o9k-update reports a NEW PILLAR,
re-run this flow to offer it — --refresh-hosts alone only syncs pillars that
are already installed.
Complete is not the goal. o9k connects frameworks; it does not sell all of
them. o9k-core is the connector and installs unasked. Everything else — the
four other pillars and the five spun-out packages — is a separate opt-in with a
default of no. A user who only wants core plus scout has a correct install,
not a partial one.
Step 0 — model check (do this before anything else)
Setup is detection + questions + installs — a cheap-model job. Check which model you are:
- Flagship active (Claude Opus/Fable, or another vendor's top model):
recommend once — "Setup doesn't need a flagship. Switch with
/model haikuand run/o9k-initagain — same result, fraction of the cost." If the user declines or just keeps going, continue — don't nag twice. - Either way: keep the main context for the interview and decisions. Push the heavy lifting — broad detection sweeps, install execution, install verification — into cheap subagents (Haiku-class) whenever the harness supports it.
Step 1 — detect
node "${CLAUDE_PLUGIN_ROOT}/scripts/o9k-init.mjs"
Read-only, instant. The first line is a Platform note — surface it to the user before the interview when it lists limitations (team-up needs tmux; native Windows needs WSL for it). Never offer something the OS can't run — skip the team-up question on native Windows and say why.
The snapshot also gives you: pillars (each with its for: / not for: line),
git, memory backend, companions, a Spun out of o9k section, bundle
deltas (what each bundle would still add), rival frameworks, open
arbitrations, a Hosts section, and an Unknown installed section
(plugins / MCPs / skills present on the machine that are not in
compat/registry.json). Detection is best-effort — "no" means not
detected, so if the user says they have a tool, believe them.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 459 lines · 80 tokens per session scan C 30304c76e355
o9k-init is a skill published in the GitHub repository Bumblebiber/its-over-9k (0 stars, last pushed 10d ago), licensed MIT. It adds 80 tokens to every session and 5,912 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (strips warnings and disclaimers, asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…